,layer_id,layer_type,param_type,shape,nparam,nnz,sparsity 0,bert.embeddings.word_embeddings,Embedding,weight,"[30522, 768]",23440896,23440896,0.0 1,bert.embeddings.position_embeddings,Embedding,weight,"[512, 768]",393216,393216,0.0 2,bert.embeddings.token_type_embeddings,Embedding,weight,"[2, 768]",1536,1536,0.0 3,bert.embeddings.LayerNorm,LayerNorm,weight,[768],768,768,0.0 4,bert.embeddings.LayerNorm,LayerNorm,bias,[768],768,768,0.0 5,bert.encoder.layer.0.attention.self.query,Linear,weight,"[320, 768]",245760,135168,0.44999998807907104 6,bert.encoder.layer.0.attention.self.query,Linear,bias,[320],320,256,0.19999998807907104 7,bert.encoder.layer.0.attention.self.key,Linear,weight,"[320, 768]",245760,149504,0.3916666507720947 8,bert.encoder.layer.0.attention.self.key,Linear,bias,[320],320,256,0.19999998807907104 9,bert.encoder.layer.0.attention.self.value,Linear,weight,"[320, 768]",245760,173056,0.2958332896232605 10,bert.encoder.layer.0.attention.self.value,Linear,bias,[320],320,256,0.19999998807907104 11,bert.encoder.layer.0.attention.output.dense,Linear,weight,"[768, 320]",245760,181248,0.26249998807907104 12,bert.encoder.layer.0.attention.output.dense,Linear,bias,[768],768,768,0.0 13,bert.encoder.layer.0.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 14,bert.encoder.layer.0.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 15,bert.encoder.layer.0.intermediate.dense,Linear,weight,"[185, 768]",142080,142080,0.0 16,bert.encoder.layer.0.intermediate.dense,Linear,bias,[185],185,185,0.0 17,bert.encoder.layer.0.output.dense,Linear,weight,"[768, 185]",142080,142080,0.0 18,bert.encoder.layer.0.output.dense,Linear,bias,[768],768,768,0.0 19,bert.encoder.layer.0.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 20,bert.encoder.layer.0.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 21,bert.encoder.layer.1.attention.self.query,Linear,weight,"[320, 768]",245760,175104,0.28749996423721313 22,bert.encoder.layer.1.attention.self.query,Linear,bias,[320],320,288,0.09999996423721313 23,bert.encoder.layer.1.attention.self.key,Linear,weight,"[320, 768]",245760,177152,0.27916663885116577 24,bert.encoder.layer.1.attention.self.key,Linear,bias,[320],320,288,0.09999996423721313 25,bert.encoder.layer.1.attention.self.value,Linear,weight,"[320, 768]",245760,166912,0.32083332538604736 26,bert.encoder.layer.1.attention.self.value,Linear,bias,[320],320,288,0.09999996423721313 27,bert.encoder.layer.1.attention.output.dense,Linear,weight,"[768, 320]",245760,167936,0.3166666030883789 28,bert.encoder.layer.1.attention.output.dense,Linear,bias,[768],768,768,0.0 29,bert.encoder.layer.1.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 30,bert.encoder.layer.1.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 31,bert.encoder.layer.1.intermediate.dense,Linear,weight,"[315, 768]",241920,241920,0.0 32,bert.encoder.layer.1.intermediate.dense,Linear,bias,[315],315,315,0.0 33,bert.encoder.layer.1.output.dense,Linear,weight,"[768, 315]",241920,241920,0.0 34,bert.encoder.layer.1.output.dense,Linear,bias,[768],768,768,0.0 35,bert.encoder.layer.1.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 36,bert.encoder.layer.1.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 37,bert.encoder.layer.2.attention.self.query,Linear,weight,"[576, 768]",442368,285696,0.3541666865348816 38,bert.encoder.layer.2.attention.self.query,Linear,bias,[576],576,480,0.1666666865348816 39,bert.encoder.layer.2.attention.self.key,Linear,weight,"[576, 768]",442368,297984,0.3263888955116272 40,bert.encoder.layer.2.attention.self.key,Linear,bias,[576],576,480,0.1666666865348816 41,bert.encoder.layer.2.attention.self.value,Linear,weight,"[576, 768]",442368,226304,0.4884259104728699 42,bert.encoder.layer.2.attention.self.value,Linear,bias,[576],576,384,0.3333333134651184 43,bert.encoder.layer.2.attention.output.dense,Linear,weight,"[768, 576]",442368,237568,0.4629629850387573 44,bert.encoder.layer.2.attention.output.dense,Linear,bias,[768],768,768,0.0 45,bert.encoder.layer.2.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 46,bert.encoder.layer.2.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 47,bert.encoder.layer.2.intermediate.dense,Linear,weight,"[339, 768]",260352,260352,0.0 48,bert.encoder.layer.2.intermediate.dense,Linear,bias,[339],339,339,0.0 49,bert.encoder.layer.2.output.dense,Linear,weight,"[768, 339]",260352,260352,0.0 50,bert.encoder.layer.2.output.dense,Linear,bias,[768],768,768,0.0 51,bert.encoder.layer.2.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 52,bert.encoder.layer.2.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 53,bert.encoder.layer.3.attention.self.query,Linear,weight,"[576, 768]",442368,277504,0.37268519401550293 54,bert.encoder.layer.3.attention.self.query,Linear,bias,[576],576,512,0.1111111044883728 55,bert.encoder.layer.3.attention.self.key,Linear,weight,"[576, 768]",442368,303104,0.31481480598449707 56,bert.encoder.layer.3.attention.self.key,Linear,bias,[576],576,512,0.1111111044883728 57,bert.encoder.layer.3.attention.self.value,Linear,weight,"[576, 768]",442368,297984,0.3263888955116272 58,bert.encoder.layer.3.attention.self.value,Linear,bias,[576],576,512,0.1111111044883728 59,bert.encoder.layer.3.attention.output.dense,Linear,weight,"[768, 576]",442368,308224,0.30324071645736694 60,bert.encoder.layer.3.attention.output.dense,Linear,bias,[768],768,768,0.0 61,bert.encoder.layer.3.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 62,bert.encoder.layer.3.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 63,bert.encoder.layer.3.intermediate.dense,Linear,weight,"[368, 768]",282624,282624,0.0 64,bert.encoder.layer.3.intermediate.dense,Linear,bias,[368],368,368,0.0 65,bert.encoder.layer.3.output.dense,Linear,weight,"[768, 368]",282624,282624,0.0 66,bert.encoder.layer.3.output.dense,Linear,bias,[768],768,768,0.0 67,bert.encoder.layer.3.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 68,bert.encoder.layer.3.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 69,bert.encoder.layer.4.attention.self.query,Linear,weight,"[576, 768]",442368,291840,0.3402777910232544 70,bert.encoder.layer.4.attention.self.query,Linear,bias,[576],576,544,0.055555522441864014 71,bert.encoder.layer.4.attention.self.key,Linear,weight,"[576, 768]",442368,310272,0.2986111044883728 72,bert.encoder.layer.4.attention.self.key,Linear,bias,[576],576,544,0.055555522441864014 73,bert.encoder.layer.4.attention.self.value,Linear,weight,"[576, 768]",442368,272384,0.38425928354263306 74,bert.encoder.layer.4.attention.self.value,Linear,bias,[576],576,480,0.1666666865348816 75,bert.encoder.layer.4.attention.output.dense,Linear,weight,"[768, 576]",442368,263168,0.40509259700775146 76,bert.encoder.layer.4.attention.output.dense,Linear,bias,[768],768,768,0.0 77,bert.encoder.layer.4.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 78,bert.encoder.layer.4.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 79,bert.encoder.layer.4.intermediate.dense,Linear,weight,"[386, 768]",296448,296448,0.0 80,bert.encoder.layer.4.intermediate.dense,Linear,bias,[386],386,386,0.0 81,bert.encoder.layer.4.output.dense,Linear,weight,"[768, 386]",296448,296448,0.0 82,bert.encoder.layer.4.output.dense,Linear,bias,[768],768,768,0.0 83,bert.encoder.layer.4.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 84,bert.encoder.layer.4.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 85,bert.encoder.layer.5.attention.self.query,Linear,weight,"[384, 768]",294912,171008,0.4201388955116272 86,bert.encoder.layer.5.attention.self.query,Linear,bias,[384],384,352,0.08333331346511841 87,bert.encoder.layer.5.attention.self.key,Linear,weight,"[384, 768]",294912,205824,0.3020833134651184 88,bert.encoder.layer.5.attention.self.key,Linear,bias,[384],384,352,0.08333331346511841 89,bert.encoder.layer.5.attention.self.value,Linear,weight,"[384, 768]",294912,217088,0.2638888955116272 90,bert.encoder.layer.5.attention.self.value,Linear,bias,[384],384,384,0.0 91,bert.encoder.layer.5.attention.output.dense,Linear,weight,"[768, 384]",294912,223232,0.243055522441864 92,bert.encoder.layer.5.attention.output.dense,Linear,bias,[768],768,768,0.0 93,bert.encoder.layer.5.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 94,bert.encoder.layer.5.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 95,bert.encoder.layer.5.intermediate.dense,Linear,weight,"[336, 768]",258048,258048,0.0 96,bert.encoder.layer.5.intermediate.dense,Linear,bias,[336],336,336,0.0 97,bert.encoder.layer.5.output.dense,Linear,weight,"[768, 336]",258048,258048,0.0 98,bert.encoder.layer.5.output.dense,Linear,bias,[768],768,768,0.0 99,bert.encoder.layer.5.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 100,bert.encoder.layer.5.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 101,bert.encoder.layer.6.attention.self.query,Linear,weight,"[448, 768]",344064,192512,0.4404761791229248 102,bert.encoder.layer.6.attention.self.query,Linear,bias,[448],448,416,0.07142853736877441 103,bert.encoder.layer.6.attention.self.key,Linear,weight,"[448, 768]",344064,224256,0.3482142686843872 104,bert.encoder.layer.6.attention.self.key,Linear,bias,[448],448,416,0.07142853736877441 105,bert.encoder.layer.6.attention.self.value,Linear,weight,"[448, 768]",344064,209920,0.3898809552192688 106,bert.encoder.layer.6.attention.self.value,Linear,bias,[448],448,352,0.21428567171096802 107,bert.encoder.layer.6.attention.output.dense,Linear,weight,"[768, 448]",344064,199680,0.4196428656578064 108,bert.encoder.layer.6.attention.output.dense,Linear,bias,[768],768,768,0.0 109,bert.encoder.layer.6.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 110,bert.encoder.layer.6.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 111,bert.encoder.layer.6.intermediate.dense,Linear,weight,"[280, 768]",215040,215040,0.0 112,bert.encoder.layer.6.intermediate.dense,Linear,bias,[280],280,280,0.0 113,bert.encoder.layer.6.output.dense,Linear,weight,"[768, 280]",215040,215040,0.0 114,bert.encoder.layer.6.output.dense,Linear,bias,[768],768,768,0.0 115,bert.encoder.layer.6.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 116,bert.encoder.layer.6.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 117,bert.encoder.layer.7.attention.self.query,Linear,weight,"[448, 768]",344064,201728,0.413690447807312 118,bert.encoder.layer.7.attention.self.query,Linear,bias,[448],448,416,0.07142853736877441 119,bert.encoder.layer.7.attention.self.key,Linear,weight,"[448, 768]",344064,237568,0.3095238208770752 120,bert.encoder.layer.7.attention.self.key,Linear,bias,[448],448,416,0.07142853736877441 121,bert.encoder.layer.7.attention.self.value,Linear,weight,"[448, 768]",344064,218112,0.3660714030265808 122,bert.encoder.layer.7.attention.self.value,Linear,bias,[448],448,352,0.21428567171096802 123,bert.encoder.layer.7.attention.output.dense,Linear,weight,"[768, 448]",344064,202752,0.4107142686843872 124,bert.encoder.layer.7.attention.output.dense,Linear,bias,[768],768,768,0.0 125,bert.encoder.layer.7.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 126,bert.encoder.layer.7.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 127,bert.encoder.layer.7.intermediate.dense,Linear,weight,"[211, 768]",162048,162048,0.0 128,bert.encoder.layer.7.intermediate.dense,Linear,bias,[211],211,211,0.0 129,bert.encoder.layer.7.output.dense,Linear,weight,"[768, 211]",162048,162048,0.0 130,bert.encoder.layer.7.output.dense,Linear,bias,[768],768,768,0.0 131,bert.encoder.layer.7.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 132,bert.encoder.layer.7.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 133,bert.encoder.layer.8.attention.self.query,Linear,weight,"[448, 768]",344064,186368,0.4583333134651184 134,bert.encoder.layer.8.attention.self.query,Linear,bias,[448],448,416,0.07142853736877441 135,bert.encoder.layer.8.attention.self.key,Linear,weight,"[448, 768]",344064,197632,0.425595223903656 136,bert.encoder.layer.8.attention.self.key,Linear,bias,[448],448,416,0.07142853736877441 137,bert.encoder.layer.8.attention.self.value,Linear,weight,"[448, 768]",344064,154624,0.550595223903656 138,bert.encoder.layer.8.attention.self.value,Linear,bias,[448],448,288,0.3571428060531616 139,bert.encoder.layer.8.attention.output.dense,Linear,weight,"[768, 448]",344064,148480,0.5684523582458496 140,bert.encoder.layer.8.attention.output.dense,Linear,bias,[768],768,768,0.0 141,bert.encoder.layer.8.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 142,bert.encoder.layer.8.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 143,bert.encoder.layer.8.intermediate.dense,Linear,weight,"[108, 768]",82944,82944,0.0 144,bert.encoder.layer.8.intermediate.dense,Linear,bias,[108],108,108,0.0 145,bert.encoder.layer.8.output.dense,Linear,weight,"[768, 108]",82944,82944,0.0 146,bert.encoder.layer.8.output.dense,Linear,bias,[768],768,768,0.0 147,bert.encoder.layer.8.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 148,bert.encoder.layer.8.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 149,bert.encoder.layer.9.attention.self.query,Linear,weight,"[320, 768]",245760,144384,0.41249996423721313 150,bert.encoder.layer.9.attention.self.query,Linear,bias,[320],320,288,0.09999996423721313 151,bert.encoder.layer.9.attention.self.key,Linear,weight,"[320, 768]",245760,155648,0.36666661500930786 152,bert.encoder.layer.9.attention.self.key,Linear,bias,[320],320,288,0.09999996423721313 153,bert.encoder.layer.9.attention.self.value,Linear,weight,"[320, 768]",245760,63488,0.7416666746139526 154,bert.encoder.layer.9.attention.self.value,Linear,bias,[320],320,160,0.5 155,bert.encoder.layer.9.attention.output.dense,Linear,weight,"[768, 320]",245760,65536,0.7333333492279053 156,bert.encoder.layer.9.attention.output.dense,Linear,bias,[768],768,704,0.08333331346511841 157,bert.encoder.layer.9.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 158,bert.encoder.layer.9.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 159,bert.encoder.layer.9.intermediate.dense,Linear,weight,"[53, 768]",40704,40704,5.960464477539063e-08 160,bert.encoder.layer.9.intermediate.dense,Linear,bias,[53],53,53,0.0 161,bert.encoder.layer.9.output.dense,Linear,weight,"[768, 53]",40704,40704,5.960464477539063e-08 162,bert.encoder.layer.9.output.dense,Linear,bias,[768],768,768,0.0 163,bert.encoder.layer.9.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 164,bert.encoder.layer.9.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 165,bert.encoder.layer.10.attention.self.query,Linear,weight,"[384, 768]",294912,158720,0.461805522441864 166,bert.encoder.layer.10.attention.self.query,Linear,bias,[384],384,320,0.16666662693023682 167,bert.encoder.layer.10.attention.self.key,Linear,weight,"[384, 768]",294912,158720,0.461805522441864 168,bert.encoder.layer.10.attention.self.key,Linear,bias,[384],384,320,0.16666662693023682 169,bert.encoder.layer.10.attention.self.value,Linear,weight,"[384, 768]",294912,77824,0.7361111044883728 170,bert.encoder.layer.10.attention.self.value,Linear,bias,[384],384,192,0.5 171,bert.encoder.layer.10.attention.output.dense,Linear,weight,"[768, 384]",294912,78848,0.7326388955116272 172,bert.encoder.layer.10.attention.output.dense,Linear,bias,[768],768,736,0.041666626930236816 173,bert.encoder.layer.10.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 174,bert.encoder.layer.10.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 175,bert.encoder.layer.10.intermediate.dense,Linear,weight,"[86, 768]",66048,66048,0.0 176,bert.encoder.layer.10.intermediate.dense,Linear,bias,[86],86,86,0.0 177,bert.encoder.layer.10.output.dense,Linear,weight,"[768, 86]",66048,66048,0.0 178,bert.encoder.layer.10.output.dense,Linear,bias,[768],768,768,0.0 179,bert.encoder.layer.10.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 180,bert.encoder.layer.10.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 181,bert.encoder.layer.11.attention.self.query,Linear,weight,"[384, 768]",294912,107520,0.6354166269302368 182,bert.encoder.layer.11.attention.self.query,Linear,bias,[384],384,256,0.3333333134651184 183,bert.encoder.layer.11.attention.self.key,Linear,weight,"[384, 768]",294912,118784,0.5972222089767456 184,bert.encoder.layer.11.attention.self.key,Linear,bias,[384],384,256,0.3333333134651184 185,bert.encoder.layer.11.attention.self.value,Linear,weight,"[384, 768]",294912,62464,0.7881944179534912 186,bert.encoder.layer.11.attention.self.value,Linear,bias,[384],384,192,0.5 187,bert.encoder.layer.11.attention.output.dense,Linear,weight,"[768, 384]",294912,54272,0.8159722089767456 188,bert.encoder.layer.11.attention.output.dense,Linear,bias,[768],768,672,0.125 189,bert.encoder.layer.11.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 190,bert.encoder.layer.11.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 191,bert.encoder.layer.11.intermediate.dense,Linear,weight,"[105, 768]",80640,80640,0.0 192,bert.encoder.layer.11.intermediate.dense,Linear,bias,[105],105,105,0.0 193,bert.encoder.layer.11.output.dense,Linear,weight,"[768, 105]",80640,80640,0.0 194,bert.encoder.layer.11.output.dense,Linear,bias,[768],768,768,0.0 195,bert.encoder.layer.11.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0 196,bert.encoder.layer.11.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0 197,qa_outputs,Linear,weight,"[2, 768]",1536,1536,0.0 198,qa_outputs,Linear,bias,[2],2,2,0.0